US10262692B2 - Method and system for automatic television production - Google Patents

Method and system for automatic television production Download PDF

Info

Publication number
US10262692B2
US10262692B2 US15/300,291 US201515300291A US10262692B2 US 10262692 B2 US10262692 B2 US 10262692B2 US 201515300291 A US201515300291 A US 201515300291A US 10262692 B2 US10262692 B2 US 10262692B2
Authority
US
United States
Prior art keywords
frame
stream
playing
scene
playing object
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US15/300,291
Other languages
English (en)
Other versions
US20170178687A1 (en
Inventor
Miki TAMIR
Gal Oz
Tal RIDNIK
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Pixellot Ltd
Original Assignee
Pixellot Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Pixellot Ltd filed Critical Pixellot Ltd
Priority to US15/300,291 priority Critical patent/US10262692B2/en
Publication of US20170178687A1 publication Critical patent/US20170178687A1/en
Assigned to PIXELLOT LTD. reassignment PIXELLOT LTD. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: RIDNIK, Tal, TAMIR, Miki, OZ, GAL
Application granted granted Critical
Publication of US10262692B2 publication Critical patent/US10262692B2/en
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
    • G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals
    • G11B27/036—Insert-editing
    • G06K9/00718—
    • G06K9/00744—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N17/00—Diagnosis, testing or measuring for television systems or their details
    • H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/21805—Source of audio or video content, e.g. local disk arrays enabling multiple viewpoints, e.g. using a plurality of cameras
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/21—Server components or server architectures
    • H04N21/218—Source of audio or video content, e.g. local disk arrays
    • H04N21/2187—Live feed
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60—Control of cameras or camera modules
    • H04N23/698—Control of cameras or camera modules for achieving an enlarged field of view, e.g. panoramic image capture
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/04—Synchronising
    • H04N5/06—Generation of synchronising signals
    • H04N5/067—Arrangements or circuits at the transmitter end
    • H04N5/073—Arrangements or circuits at the transmitter end for mutually locking plural sources of synchronising signals, e.g. studios or relay stations
    • H04N5/0733—Arrangements or circuits at the transmitter end for mutually locking plural sources of synchronising signals, e.g. studios or relay stations for distributing synchronisation pulses to different TV cameras
    • H04N5/23238—
    • H04N5/247—
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/76—Television signal recording
    • H04N5/765—Interface circuits between an apparatus for recording and another apparatus
    • H04N5/77—Interface circuits between an apparatus for recording and another apparatus between a recording apparatus and a television camera
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Definitions

  • the present disclosed subject matter is directed to methods and systems for automatic outdoors television productions.
  • the disclosure deals with television production of sports events.
  • the present invention is based on fully automatic operation of cameras by a server deployed in or close to the field.
  • Several cameras capture a panoramic view of the playing field.
  • the server uses the captured images to operate virtual camera, the leading camera “camera 1” for example, thus replacing cameramen.
  • the server also switches between virtual cameras.
  • the server uses directed sensors which are also deployed in the field.
  • the present invention provides a computer-implemented method for producing a video scene.
  • the method includes receiving, from several video cameras, a stream of video images of the scene for capturing a panoramic view of the scene, analyzing the stream of video images, and determining location data of frame streams in accordance with the analyzing.
  • the method also includes rendering an active frame stream of the one or more frame streams with images corresponding to a portion of the panoramic view of the scene, based on the location data.
  • the method enables transmitting for broadcasting the rendered stream of image frames corresponding to the respective portion of the panoramic view.
  • the step of analyzing the images includes identifying a primary object in the stream of video images, tracking the primary object, and identifying at least one secondary object associated with the primary object.
  • the method includes calibrating the cameras using points in a playing field.
  • Exemplary points are corners of the playing field, crossings of two field lines, 11 m penalty kick point, beacon points deployed in the playing field and having locations determined by geodic devices, and a bench related point.
  • a parameter set defines a frame stream by parameters relating to location, digital zooming, and time.
  • Location parameters include a left angle, a right angle, a bottom angled a top angle, a central angular coordinate, a central location coordinate, an aspect ratio, and a frame width.
  • Zooming parameters are a fixed zoom parameter, parameters of an equation defining a dependence of a zoom parameter on a timestamp, and a table of zoom parameter versus a timestamp.
  • Temporal parameters include a current time flag, a start timestamp, a final timestamp, a frame rate, and a resolution parameter.
  • the frame width is determined, for example, by a predetermined width, a predetermined number of players in the frame, a prohibition flag related to exceeding playing field boundaries, and a demand flag related to including a key static object in the frame.
  • the method includes estimating a region occupying a playing object upon losing the playing object, and modifying the frame stream to include the region.
  • the method includes validating the identification of a playing object at a certain time in a certain location, by estimating a probability of playing object presence thereof in view of a playing object orbit before the certain time.
  • the method includes determining a frame center in accordance with variables like a playing object location, and a center of mass of player locations.
  • the method includes smoothing a playing object orbit, and determining a center frame in accordance with the smoothed playing object orbit, thus preventing jerky movement of a frame center orbit.
  • the method includes identifying a fast break in a basketball match, estimating a ball speed, and selecting a location of a frame for blocking a player group in dependence on the ball speed.
  • a front side of the fast break is selected in case of a fast ball, and a rear side thereof is selected in ease of a slow ball.
  • frames are determined by a rectangle blocking a predetermined portion of the players.
  • the present invention also provides a method for a computerized server autonomously producing a TV show of a sports game in a scene.
  • the method includes receiving from several cameras a stream of video images of the scene for capturing a panoramic view of the scene, providing several parameter sets defining several respective frame streams, selecting an initial active frame stream in accordance with a predetermined rule.
  • the method further includes rendering the active frame stream with images corresponding to a respective portion of a panoramic view of the scene in accordance with the respective parameter set of the selected frame stream.
  • the method enables transmitting for broadcasting the rendered, stream of image frames corresponding to the respective portion of the panoramic view.
  • the method also includes analyzing the stream of video images for identifying an event in the scene for switching between the active frame stream and a different frame stream, and replacing the active frame stream by the different frame stream.
  • Exemplary events are a match start-up, a match end, a match break, a time-out start, a time-out end, an 11 meter penalty kick, a break end, an offside, a corner kick, a free kick, and throw-in.
  • the event may be either an occurring event or an event expected to occur.
  • the respective plurality of frame streams are associated to respective views.
  • Exemplary views are a broad playing object view, a narrow playing object view, two fixed gate views, two fixed basket views, several fixed audience view, several replay views, and a moving camera view.
  • a replacement of a frame stream associated with a broad playing object view by a frame stream associated with a narrow playing object view is triggered by a decrease of playing object speed to a speed under a predetermined value for at least a predetermined time period.
  • the replacement may also be triggered by an event of a static playing object waiting to an identified game situation.
  • the method includes switching to a replay frame stream for presenting, a replay of an identified dramatic event.
  • the present invention provides a method for a computerized server autonomously producing a TV show of a sports match in a scene, enhanced by directed sensors.
  • the method includes receiving from several video cameras a stream of video images of the scene for capturing a panoramic view of the scene, and defining several frame streams by location data in accordance with predetermined rules and with analysis of the stream of video images.
  • the method further includes selecting an active frame in accordance with a predetermined procedure and, in accordance with an analysis of the stream of video images, and directing a directed sensor to a region of interest in accordance with location data of the active frame stream.
  • the method includes rendering an active frame stream with images corresponding to a respective portion of the panoramic view of the scene, and transmitting for broadcasting the rendered stream of image frames.
  • the method includes analyzing the stream of video images for allowing definition of the frame streams.
  • the method includes analyzing the stream of video images in accordance with predetermined criteria characterizing situations occurring in the scene, identifying a situation occurring in the region of interest as being characterized by a criterion, and triggering actions related to the directed sensor. Exemplary actions are capturing a signal using the directed sensor, and broadcasting the captured signal.
  • the method includes calibrating a pan-tilt-zoom (PTZ) video camera in reference to the scene to allow directing the PTZ video camera to the region of interest in accordance with the location data.
  • the method includes calibrating pan and tilt angles of the PTZ camera while being pointed on two or more points in the scene.
  • the method includes directing the PTZ video camera to the region of interest for capturing a video signal thereof.
  • PTZ pan-tilt-zoom
  • the method includes directing a directional microphone to the region of interest and recording an audio signal generated thereof.
  • the method further includes selecting the audio signal generated thereof for broadcasting as an audio signal of a broadcasted stream of images associated with the active frame stream.
  • FIG. 1 a is a block diagram of an automatic television production system
  • FIG. 1 b illustrates a soccer playing field equipped with several sensors capturing images and audio signal for automatic television production
  • FIG. 2 a is a flow chart of a method for automatic television production
  • FIG. 2 b is a flow chart of object steps in a method for automatic television production
  • FIG. 3 is a flow chart of a method for automatic switching between frame streams in automatic television production.
  • FIG. 4 is a flow chart of a method for enhancing automatic television production by directed sensors.
  • each of the verbs “comprise”, “include” and “have”, and conjugates thereof, are used to indicate that the object or objects of the verb are not necessarily a complete listing of members, components, elements or parts of the subject or subjects of the verb.
  • FIG. 1 a there is described a system 100 for low cost automatic television production, which includes a data server 115 in a venue 105 , several sensors which capture a panoramic view of a playing field of a sports game, and facilities to broadcast the TV production.
  • a data server 115 in a venue 105
  • several sensors which capture a panoramic view of a playing field of a sports game, and facilities to broadcast the TV production.
  • an automatic method to operate a virtual camera leading camera “camera 1” for example, is described, thus replacing a cameraman.
  • an automatic method for switching between virtual cameras is outlined.
  • an enhanced method for automatic TV production using directed sensors is described.
  • FIGS. 1 a , 1 b , 1 b , 2 b Automatic Operation of a Virtual Camera
  • a system for automatic TV production is illustrated in the venue 100 of FIG. 1 a and a scene 155 of FIG. 1 b .
  • three fixed cameras 110 , 111 and 112 combine to capture a panoramic view 131 of a selected location, for example, a playing field, such as a soccer field 160 .
  • a pan-tilt-zoom (hereafter PTZ) camera 115 may be directed to a region of interest (ROI) in the field, ROI 180 for example, from a different direction.
  • ROI region of interest
  • a directed microphone 117 may be aligned to an ROI in the field, ROI 180 in the example of FIG. 1 b , to capture audio signal generated thereof, like shouts of players 176 and 178 .
  • the cameras 110 , 111 , and 112 are frame synchronized. Each camera is capturing video images of a certain zone of the scene 155 . A lens is adjusted for each camera to fully cover the zone.
  • a method of optimal coverage of the venue composed of lenses with a variety of focal lengths and cameras with different number and size of horizontal and vertical pixels may be used by packing simulation techniques.
  • neighboring (adjacent) cameras have overlapping coverage zones.
  • the cameras 110 , 111 , and 112 may be CMOS (complementary metal-oxide-semiconductor) or CCD (semiconductor charge-coupled devices) cameras. Each camera may be composed of a single or multiple, e.g., three, imagers. Preferably, the cameras are of industrial grade.
  • the data output format of the cameras can be GigE, USB 3.0, Camera Link, HD-SDI or any other format available for such cameras.
  • a single wide angle camera 111 may provide a panoramic view, despite being the only sensor capturing the scene.
  • sensors 110 - 112 , 116 and 117 are communicating with a sensor interface 120 of the venue server 115 , which in turn, feeds a broadcasting facility 142 or a webcasting facility 145 via an output formatting module 135 .
  • Data transmission from the cameras 110 - 112 to the data server 115 may be done via optical cable or any other wired or wireless communication system.
  • the cameras 110 - 112 have GigE output and a network switch with fiber optical cable used to transfer the data to the data server 115 .
  • the cameras data can also be transferred using the worldwide web.
  • the venue server 115 includes the following modules:
  • the server 115 calibrates the video cameras 110 - 112 , as well as PTZ camera 116 using points in the playing field 160 .
  • Exemplary points are corners 162 and 164 of the soccer field 160 , crossings of two field lines 172 , 11 m penalty kick spot 183 , beacon points deployed in the playing field and having locations determined by geodic devices, and a bench related point.
  • the calibration data is stored in a sensor calibration database 150 .
  • the calibration data of the cameras and geometrical calculation are used for two tasks.
  • the images received from the cameras are associated to each other such, as to define the Panoramic view.
  • the location data of a frame stream is related to angular or Cartesian coordinates of the panoramic view.
  • the server 115 uses frame streams as virtual cameras, counterparts of real cameras in a traditional TV production of sports games.
  • the frame streams are stored in respective parameter sets or data records in a frame stream database 140 .
  • a parameter set defines a frame stream by parameters related to location, zooming and time.
  • Typical location parameters are a left angle, a right angle, a bottom angle, a top angle, a central angular coordinate, a central location coordinate, an aspect ratio, a frame width, and a resolution parameter.
  • the aspect ratio may have a fixed value of 16:9.
  • Typical zooming parameters are a fixed zoom parameter, parameters of an equation defining a dependence of a zoom parameter on a timestamp, and values in a table of zoom parameter versus a timestamp.
  • the zoom value is used for digital zooming of the panoramic view using the images captured by cameras 110 - 112 which may be fixed cameras without any real zoom capability.
  • Typical temporal parameters are a current time flag, a start timestamp, a final timestamp, and a frame rate.
  • a positive current, time flag indicates that the frame stream follows real time as much as possible.
  • Frame width may be a predetermined fixed width for fixed cameras like agate or a basket camera.
  • the frame width fulfills a certain, condition.
  • One exemplary condition is that a predetermined number of players is present in the frame.
  • Another exemplary condition is that the frame does not exceed playing field boundaries.
  • a third exemplary condition is that a key static object like a gate 170 or a basket is included in the frame.
  • the sensor interface 120 receives from video cameras 110 - 112 a stream of video images of the playing field 160 , thus capturing a panoramic view thereof.
  • an analyzing module 125 analyses the stream of video images for allowing definition of several frame streams. Consequently, in step 225 the analyzing module 125 determines location, zooming and time parameters of the frame streams and store them in the frame stream database 140 .
  • a module 130 renders an active frame stream with images corresponding to a respective portion of the panoramic view of the scene.
  • the active frame stream may be the only frame stream, a counterpart of “a camera 1”, for example.
  • the resulted production is the same as having a single real cameraman capturing the scene 155 in a low league match.
  • a leading virtual camera (“camera 1”) is normally generating a wide FOV typically comprising one third of the playing field.
  • “Camera 2” frame stream provides a tighter view of the ball vicinity.
  • There are other virtual cameras providing close-up views on players groups or individual players. Accordingly, there are several frame streams and the executed analysis determines parameter set for most of the frame streams, while only one is an active frame stream having rendered images. The selection of an active frame stream and the switching between frame streams is further discussed in the next section.
  • the active frame filling module 130 adjusts the color and brightness of the images captured by cameras 110 - 112 , which contribute to rendering the active frame stream, and transforms between images originated at different cameras from world coordinates to camera coordinates.
  • the module 130 blends the pixels in stitching zones encompassing the stitching lines, and geometrically aligns the outputs of the different cameras 110 - 112 using one of the methods known in prior art for calibrating and aligning images captured by several cameras.
  • output formatting module 135 formats the rendered image frame stream for broadcasting or webcasting and communicate the result streams to a broadcasting facility 142 or to a webcasting facility 145 .
  • the method includes a step 255 of identifying a primary object, such as a ball 172 , a step 258 of tracking the object 172 , a step 260 of identifying players 176 and 178 associated with, the ball 172 , and a step 265 of estimating a region, occupying the hall upon losing it.
  • the ball 172 and the players 176 and 178 are detected and tracked throughout the play using dynamic background subtraction for creating blobs that represent the respective players.
  • Automatic ball tracking in sports games is disclosed, for example, in US Pub. No. 2008/0312010 to Marty etal, and in US Pub. No. 2011/0267461 to Birnboim etal, Player identification is disclosed, for example, in US Pub. No. 2012/0013711 to Tamir and Wilf.
  • Event detection and ball tracking is discussed in “Multimedia” edited by K. Nishi, 2010, Chapter 10 by Ariki and Takiguchi entitled “Digital Camera Work for Soccer Video Production with Event Detection and Accurate Ball Tracking by. Switching Search Method”, Ball orbit or trajectory may be two-dimensional if the ball is captured from only one direction, or three dimensional if the ball is captured from two directions.
  • the analyzing module 125 modifies the frame stream such that a “camera 1” frame includes the region which occupies the ball.
  • a frame center may be determined such as to follow a ball location or to follow a center of mass of player locations.
  • the analyzing module 125 smoothes a ball orbit. Consequently, in step 280 , module 125 determines a center frame in accordance with the smoothed ball orbit.
  • module 125 validates the identification of the ball 172 at a certain time in a certain location by estimating a probability of the ball 172 presence thereof in view of the ball orbit before the certain time.
  • Steps 283 , 285 and 290 may be executed whenever the captured game is basketball.
  • module 125 identifies a fast break, then it estimates the speed of ball 172 , and finally it selects a location of a frame blocking a player group dealing with ball 172 in dependence on the ball speed.
  • a front side of the fast break is selected in case of a fast ball, and a rear side thereof is selected in a case of a slow ball.
  • module 125 determines the parameter set of a frame stream by blocking a predetermined portion of the players 176 and 178 by a rectangle.
  • a predetermined portion of the players 176 and 178 Preferably, in certain games, most of the players 176 or all of them are included in a frame stream of “camera 1”. Sometimes, at least three or five players 178 are included in a frame stream.
  • FIGS. 1 a , 1 b , 3 Automatic Director Embodiment
  • FIG. 3 outlines a flow chart of a method 300 for automatic switching between frame streams in an automatic TV production of a sports game.
  • the server 115 uses frame streams as virtual cameras, counterparts of real cameras in a traditional TV production of sports games.
  • the frame streams are stored in respective parameter sets or data records in a frame stream database 140 .
  • a parameter set defines a frame stream by parameters related to location, zooming and time, as detailed above.
  • default or preliminary values are stored in frame stream database 140 for several frame streams. For example, a center of a “camera 1” frame stream may be initially set to ball position when a game starts.
  • the frame streams are, associated to respective views.
  • Exemplary views are a broad ball view “camera 1” a narrow ball view “camera 2”, two fixed gate views, two fixed basket views, several fixed audience view, several replay views, and a moving camera view.
  • the sensor interface 120 receives from video cameras 110 - 112 a stream of video images of the playing field 160 , thus capturing a panoramic view thereof.
  • module 125 selects an initial active frame in accordance with a predetermined rule.
  • An exemplary rule is that the initial frame stream is “camera 1” frame stream.
  • module 130 renders the active frame stream with images imaging a respective portion of the panoramic view of the scene 155 .
  • the analyzing module 125 analyses the stream of video images, trying to identify an event which triggers switching between the active frame stream and a different frame stream.
  • Event identification is based on player and ball identification and on familiarity with typical game situations. In soccer, for example, a throw-in event is identified as a situation when a player is standing on a touch-line with a ball over his head. Consequently, in step 360 , module 125 replaces the active frame stream by a different frame stream. Module 125 also uses sports type photographing rules, like switch from “camera 1” to “camera 2”, if the ball 172 is currently in the goal area or if the ball 172 is moving slowly and players 176 an 178 are crowded around the ball 172 .
  • Module 125 may also decide to switch from “camera 1” or “camera 2” to a close-up view if the ball is stationary and there is a single player close to it. Let alone the active frame stream, all frame streams having no rendered images. However, a transition between frame streams may occur gradually such that two frame streams are presented simultaneously with the old one fading out while the new one takes over. Other transition effects like wipe are also possible.
  • the module 125 may select the desired transition in accordance with a predetermined procedure. For the short duration of the transition, two frame streams may be rendered with images simultaneously.
  • Exemplary events identified by module 125 are a match start-up, a match end, a match break, a time-out start, a time-out end, an 11 meter penalty kick, a break end, an offside, a corner kick, a free kick, and throw-in.
  • the identified event may be either an occurring event or an event expected to occur.
  • a “camera 1” frame stream is replaced by a “camera 2” frame stream once a decrease occurs of ball speed to a speed under a predetermined value for at least a predetermined time period.
  • Typical predetermined speed value are 5, 8 10, 12 and 15 km per hour.
  • Typical predetermined, time periods are 4, 6, 7 and 10 sec.
  • module 125 identifies that the ball 172 is completely static in preparation to an identified match situation like a corner kick.
  • module 125 switches the active frame stream to a replay frame stream for presenting a close-up slow replay of the identified event, after which the active frame strewn is switched back to “camera 1” frame stream.
  • the start timestamp of the replay frame stream is several seconds before the goal kick, and the final, timestamp is several seconds after the goal, while the frame rate is one third of the regular rate, for example.
  • the transition between active frame streams occurs in arbitrary points of time. Usually, once an active frame stream is selected it stays on air until further selection. Sometimes, like in the case of a reply frame stream, it ends in accordance with a final timestamp and other frame stream is selected to be the active one according to a predetermined rule. For example, a rule may determine that at the end of a replay, the “camera 1” frame stream is again the active one.
  • FIGS. 1 a , 1 b , 4 Automatic TV Production with Directed Sensor
  • Sports event producers need to capture the event from more than a single perspective.
  • the proposed system may have just a single perspective. It is of course possible to use multiple camera arrays, each located in its unique location in the venue. For example, in a soccer match, the production team may decide to use three camera heads and deploy the first one in a mid court position and the other two behind the respective two gates to cover the respective goal keeper.
  • a better embodiment of the multi-perspective configuration is, based on a single camera head or a camera array composed of multiple fixed cameras covering the playing field and a camera with an automatic remotely controlled zoom lens mounted on a remotely controlled pan and tilt unit.
  • An automatic sound capture device may cover the game as well.
  • a directional microphone 117 is mounted on a remotely controlled pan and tilt unit.
  • the microphone 117 may be slaved to FOV coordinates compatible with a certain frame stream to cover a player or group of players related to a situation in which the capture of sound might be beneficial. Such situations may be, for example two quarreling players or a referee yelling at one of the players.
  • Exemplary directional microphones are parabolic microphones, flat directed microphones, microphones with running wave and gradient microphones. These microphones are known in the art to provide directivity and sensitivity for capturing audio signal generated in portions of the playing field.
  • FIG. 4 there is described a flow chart of a method 400 for a computerized server autonomously producing a TV show of a sports game in a scene, whereas the method is enhanced by using directed sensors in addition to fixed video cameras.
  • Sever 115 controls a pan-tilt-zoom (PTZ) camera 116 and a directed microphone 117 using the sensor interface 120 .
  • Directed microphone 117 is disposed on an alignable two-axis base.
  • analyzing module 125 calibrates the PTZ video camera 116 in reference to the scene to allow its directing to the region of interest in accordance with the location data of a frame stream.
  • pan and tilt angles of the PTZ camera are pointed on several points in the scene, and the calibration data is stored in a sensor calibration database 150 . The stored calibration data is used to align the PTZ camera 116 in accordance with location data of a frame stream.
  • the sensor interface 120 receives from video cameras 110 - 112 a stream of video images of the playing field 160 , thus capturing a panoramic view thereof. Consequently, in step 225 , the analyzing module 125 determines location, zooming and time parameters of the frame streams and store them in the frame stream database 140 . In step 330 , module 125 selects an initial active frame in accordance with a predetermined rule and in accordance with an analysis of the images. In step 230 , module 130 renders the active frame stream with images imaging a respective portion of the panoramic view of the scene 155 , and in step 235 the rendered stream of images is broadcasted.
  • module 125 directs the directed sensor 116 or 117 to a region of interest in accordance with location data of the active frame stream. Also, in step 350 , the module 125 analyzes the stream of video images in accordance with predetermined criteria characterizing situations occurring in the scene. Thus, in step 440 , module 125 identifies a situation occurring in the region of interest as being characterized by an appropriate criterion, and triggers actions related to the directed sensor. In an action 450 , the directed sensor 116 or 117 captures a signal, and in an action 460 , server 115 broadcasts the captured signal.
  • module 125 directs the PTZ video camera 116 to the region of interest for capturing a video signal thereof, and according to an identified situation the active frame stream is replaced on air for a while by the captured signal. For example, if the identified situation calls for a zoom larger than available digitally using a digital zooming capability of a frame stream, then the directed PTZ camera 116 may provide the desired enlarged real zooming capability.
  • Module 125 may direct the directional microphone 117 to the region of interest and for recording an audio signal generated thereof. Module 125 may select that audio signal for broadcasting as an audio signal of a broadcasted stream of visual images rendered to, the active frame stream.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Studio Devices (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
US15/300,291 2014-04-03 2015-03-31 Method and system for automatic television production Active 2035-10-29 US10262692B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US15/300,291 US10262692B2 (en) 2014-04-03 2015-03-31 Method and system for automatic television production

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201461974460P 2014-04-03 2014-04-03
PCT/IL2015/050346 WO2015151095A1 (en) 2014-04-03 2015-03-31 Method and system for automatic television production
US15/300,291 US10262692B2 (en) 2014-04-03 2015-03-31 Method and system for automatic television production

Publications (2)

Publication Number Publication Date
US20170178687A1 US20170178687A1 (en) 2017-06-22
US10262692B2 true US10262692B2 (en) 2019-04-16

Family

ID=54239494

Family Applications (1)

Application Number Title Priority Date Filing Date
US15/300,291 Active 2035-10-29 US10262692B2 (en) 2014-04-03 2015-03-31 Method and system for automatic television production

Country Status (7)

Country Link
US (1) US10262692B2 (he)
EP (1) EP3127321B1 (he)
JP (1) JP7123523B2 (he)
CN (2) CN113873174A (he)
ES (1) ES2845933T3 (he)
IL (1) IL247879B (he)
WO (1) WO2015151095A1 (he)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11882363B2 (en) 2020-10-05 2024-01-23 Canon Kabushiki Kaisha Control apparatus and learning apparatus and control method

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10600245B1 (en) * 2014-05-28 2020-03-24 Lucasfilm Entertainment Company Ltd. Navigating a virtual environment of a media content item
US9961385B2 (en) * 2015-07-27 2018-05-01 Tribune Broadcasting Company, Llc News production system with program schedule modification feature
DE102016224095A1 (de) * 2016-12-05 2018-06-07 Robert Bosch Gmbh Verfahren zum Kalibrieren einer Kamera und Kalibriersystem
US10425643B2 (en) * 2017-02-04 2019-09-24 OrbViu Inc. Method and system for view optimization of a 360 degrees video
JP6965975B2 (ja) * 2017-03-10 2021-11-10 株式会社Ｊｖｃケンウッド 映像処理装置、マルチカメラシステム、映像処理方法、及び映像処理プログラム
JP6766707B2 (ja) * 2017-03-10 2020-10-14 株式会社Ｊｖｃケンウッド 映像処理装置、マルチカメラシステム、映像処理方法、及び映像処理プログラム
CN107241611B (zh) * 2017-05-27 2019-09-24 蜜蜂四叶草动漫制作(北京)有限公司 一种直播联动装置及直播联动系统
CN109151295B (zh) 2017-06-16 2020-04-03 杭州海康威视数字技术股份有限公司 一种目标对象抓拍方法、装置及视频监控设备
JP7303754B2 (ja) 2017-06-27 2023-07-05 ピクセルロット エルティーディー． ユーザー固有コンテンツを映像制作に融合させる方法及びシステム
US11310418B2 (en) * 2018-01-19 2022-04-19 Veo Technologies Aps Computer-implemented method for automated detection of a moving area of interest in a video stream of field sports with a common object of interest
JP7250440B2 (ja) * 2018-05-31 2023-04-03 キヤノン株式会社 撮影装置、情報処理装置、情報処理方法、およびプログラム
US10841509B2 (en) 2018-10-22 2020-11-17 At&T Intellectual Property I, L.P. Camera array orchestration
US11606493B2 (en) * 2018-11-14 2023-03-14 Samsung Electronics Co., Ltd. Method for recording multimedia file and electronic device thereof
CA3146833A1 (en) * 2019-07-09 2021-01-14 Hyphametrics, Inc. Cross-media measurement device and method
KR102112517B1 (ko) * 2020-03-06 2020-06-05 모바일센 주식회사 실시간 영상 분석을 통한 카메라 위치 제어 및 영상 편집을 통한 무인 스포츠 중계 서비스 방법 및 이를 위한 장치
CN111787337A (zh) * 2020-03-09 2020-10-16 北京理工大学 一种电视直播方案辅助设计方法
CN111787339A (zh) * 2020-03-09 2020-10-16 北京理工大学 一种直播预演系统
CN111787338A (zh) * 2020-03-09 2020-10-16 北京理工大学 一种体育赛事直播方案辅助设计方法
EP3945464B1 (en) 2020-07-29 2024-07-17 Optima Sports Systems S.L. A computing system and a computer-implemented method for sensing events from geospatial data
US11640713B2 (en) 2020-07-29 2023-05-02 Optima Sports Systems S.L. Computing system and a computer-implemented method for sensing gameplay events and augmentation of video feed with overlay
CN111711733B (zh) * 2020-08-18 2020-11-13 北京理工大学 一种直播方案仿真设计验证方法
EP4235489A1 (en) * 2020-10-22 2023-08-30 Pixelscope Inc. Device and method for determining image for sports broadcasting, and recording medium in which command is recorded
AU2022210466A1 (en) * 2021-01-25 2023-07-13 EmergeX, LLC Methods and system for coordinating uncoordinated content based on multi-modal metadata through data filtration and synchronization in order to generate composite media assets
CN118075552B (zh) * 2024-04-22 2024-06-28 黑龙江省邦盾科技有限公司 一种演播室视频特征图像增强处理方法

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0746582A (ja) 1993-07-28 1995-02-14 Nippon Telegr & Teleph Corp <Ntt> 映像切り出し方法
US5745126A (en) * 1995-03-31 1998-04-28 The Regents Of The University Of California Machine synthesis of a virtual video camera/image of a scene from multiple video cameras/images of the scene in accordance with a particular perspective on the scene, an object in the scene, or an event in the scene
US20030179294A1 (en) * 2002-03-22 2003-09-25 Martins Fernando C.M. Method for simultaneous visual tracking of multiple bodies in a closed structured environment
JP2004046647A (ja) 2002-07-12 2004-02-12 Univ Waseda 動画像データに基づく移動物体追跡方法及び装置
EP1480450A2 (en) 2003-05-20 2004-11-24 British Broadcasting Corporation Automated video production
JP2006040199A (ja) 2004-07-30 2006-02-09 Nippon Hoso Kyokai <Nhk> 映像オブジェクト抽出装置、映像オブジェクト軌跡合成装置、その方法及びそのプログラム
US20070279494A1 (en) * 2004-04-16 2007-12-06 Aman James A Automatic Event Videoing, Tracking And Content Generation
US20080312010A1 (en) * 2007-05-24 2008-12-18 Pillar Vision Corporation Stereoscopic image capture with performance outcome prediction in sporting environments
US20090284601A1 (en) * 2008-05-15 2009-11-19 Jayakrishnan Kumar Eledath Apparatus for intelligent and autonomous video content generation and streaming
US7796155B1 (en) * 2003-12-19 2010-09-14 Hrl Laboratories, Llc Method and apparatus for real-time group interactive augmented-reality area monitoring, suitable for enhancing the enjoyment of entertainment events
US20110267461A1 (en) * 2010-05-03 2011-11-03 Stats Llc Trajectory detection and analysis in sporting events
US20120013711A1 (en) 2009-04-08 2012-01-19 Stergen Hi-Tech Ltd. Method and system for creating three-dimensional viewable video from a single video stream
US20120057852A1 (en) 2009-05-07 2012-03-08 Christophe Devleeschouwer Systems and methods for the autonomous production of videos from multi-sensored data
WO2014024475A1 (ja) 2012-08-10 2014-02-13 パナソニック株式会社 映像提供方法、送信装置および受信装置
WO2014191990A1 (en) 2013-05-26 2014-12-04 Pixellot Ltd. Method and system for low cost television production

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4934094B2 (ja) * 2008-05-09 2012-05-16 日本放送協会 スポーツ映像送出装置
JP5202127B2 (ja) * 2008-06-17 2013-06-05 キヤノン株式会社 映像配信装置及び映像配信方法
US9615064B2 (en) * 2010-12-30 2017-04-04 Pelco, Inc. Tracking moving objects using a camera network

Patent Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0746582A (ja) 1993-07-28 1995-02-14 Nippon Telegr & Teleph Corp <Ntt> 映像切り出し方法
US5745126A (en) * 1995-03-31 1998-04-28 The Regents Of The University Of California Machine synthesis of a virtual video camera/image of a scene from multiple video cameras/images of the scene in accordance with a particular perspective on the scene, an object in the scene, or an event in the scene
US20030179294A1 (en) * 2002-03-22 2003-09-25 Martins Fernando C.M. Method for simultaneous visual tracking of multiple bodies in a closed structured environment
JP2004046647A (ja) 2002-07-12 2004-02-12 Univ Waseda 動画像データに基づく移動物体追跡方法及び装置
EP1480450A2 (en) 2003-05-20 2004-11-24 British Broadcasting Corporation Automated video production
US7796155B1 (en) * 2003-12-19 2010-09-14 Hrl Laboratories, Llc Method and apparatus for real-time group interactive augmented-reality area monitoring, suitable for enhancing the enjoyment of entertainment events
US20070279494A1 (en) * 2004-04-16 2007-12-06 Aman James A Automatic Event Videoing, Tracking And Content Generation
JP2006040199A (ja) 2004-07-30 2006-02-09 Nippon Hoso Kyokai <Nhk> 映像オブジェクト抽出装置、映像オブジェクト軌跡合成装置、その方法及びそのプログラム
US20080312010A1 (en) * 2007-05-24 2008-12-18 Pillar Vision Corporation Stereoscopic image capture with performance outcome prediction in sporting environments
US20090284601A1 (en) * 2008-05-15 2009-11-19 Jayakrishnan Kumar Eledath Apparatus for intelligent and autonomous video content generation and streaming
US20120013711A1 (en) 2009-04-08 2012-01-19 Stergen Hi-Tech Ltd. Method and system for creating three-dimensional viewable video from a single video stream
US20120057852A1 (en) 2009-05-07 2012-03-08 Christophe Devleeschouwer Systems and methods for the autonomous production of videos from multi-sensored data
US20110267461A1 (en) * 2010-05-03 2011-11-03 Stats Llc Trajectory detection and analysis in sporting events
WO2014024475A1 (ja) 2012-08-10 2014-02-13 パナソニック株式会社 映像提供方法、送信装置および受信装置
WO2014191990A1 (en) 2013-05-26 2014-12-04 Pixellot Ltd. Method and system for low cost television production

Non-Patent Citations (9)

* Cited by examiner, † Cited by third party
Title
Ariki et al; Digital Camera Work for Soccer Video Production with Event Detection and Accurate Ball Tracking by Switching Search Method; Multimedia; 2010, Chapter 10.
Information Technology Letters, The Institute of Electronics, Information and Communication Engineers and Information Processing Society of Japan, vol. 5., 2006.
Office Action dated Jan. 8, 2019 for Japanese application No. 2016-559211.
Qihe et al, Automatic Camera Calibration for images of Soccer Match, 2007. *
Search Report dated Jul. 28, 2015 for corresponding International Application No. PCT/IL2015/050346.
Search Report dated Mar. 13, 2017 for corresponding European Application No. 15772324.8.
Technical Report, the Institute of Image Information and Television Engineers (ITE), vol. 37, No. 36, Aug. 12, 2013.
The transactions of the institute of electronics, information and communication engineers D-11; vol. J86-D-11, No. 3, Mar. 2003.
Vasanth et al, Detecting Semantic Events in Soccer Games: Towards a Complete Solution, 2001. *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11882363B2 (en) 2020-10-05 2024-01-23 Canon Kabushiki Kaisha Control apparatus and learning apparatus and control method

Also Published As

Publication number Publication date
CN113873174A (zh) 2021-12-31
EP3127321A4 (en) 2017-04-12
WO2015151095A1 (en) 2015-10-08
IL247879A0 (he) 2016-11-30
IL247879B (he) 2020-01-30
JP2017513385A (ja) 2017-05-25
ES2845933T3 (es) 2021-07-28
EP3127321A1 (en) 2017-02-08
EP3127321B1 (en) 2020-12-23
JP7123523B2 (ja) 2022-08-23
CN106165393A (zh) 2016-11-23
US20170178687A1 (en) 2017-06-22

Similar Documents

Publication Publication Date Title
US10262692B2 (en) Method and system for automatic television production
US10438633B2 (en) Method and system for low cost television production
US8848066B2 (en) Method and an apparatus for generating image content
US8013899B2 (en) Camera arrangement and method
AU2022201303A1 (en) Selective capture and presentation of native image portions
CN105765959B (zh) 用于制作视频作品的方法和系统
US20180225852A1 (en) Apparatus and method for generating best-view image centered on object of interest in multiple camera images
US20120013711A1 (en) Method and system for creating three-dimensional viewable video from a single video stream
WO2018094443A1 (en) Multiple video camera system
CN107005654A (zh) 用于光学跟踪运动场地中的运动员的系统和方法
US20130335520A1 (en) Robotic Camera System with Context Display
CN107431846A (zh) 基于多个摄像机的图像传输方法、设备和系统
CN108600771A (zh) 录播工作站系统及操作方法
US20240303835A1 (en) Image capturing system and method
EP4429234A1 (en) Image capturing system and method
JP7505838B1 (ja) 撮像システム、撮像プログラム、及び撮像方法
NZ719619A (en) Selective capture and presentation of native image portions
NZ719619B2 (en) Selective capture and presentation of native image portions

Legal Events

Date Code Title Description
AS Assignment

Owner name: PIXELLOT LTD., ISRAEL

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:TAMIR, MIKI;OZ, GAL;RIDNIK, TAL;SIGNING DATES FROM 20181008 TO 20181009;REEL/FRAME:047597/0543

STCF Information on status: patent grant

Free format text: PATENTED CASE

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YR, SMALL ENTITY (ORIGINAL EVENT CODE: M2551); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY

Year of fee payment: 4